Tool Calling and Structured Output are two core capabilities of modern Agent systems, yet their interaction under joint deployment conditions remains insufficiently understood. This paper reports a reproducible phenomenon observed in a production Agent system: when Tool Calling and JSON Schema constraints are simultaneously enabled, multiple open-weight models cease invoking tools despite maintaining high schema compliance.
arXiv:2607. 00035v1 Announce Type: new Abstract: LLMs and agents can generate web scrapers from natural-language requirements, but direct generation remains unreliable because of dependency errors, broken selectors, schema mismatches, and heterogeneous page structures.
By Bo Chen
arXiv:2609.23742v1 Announce Type: new
Abstract: Small open-source large language models (LLMs) in the 0.6B-4B parameter range are increasingly deployed for structured output generation (JSON, functio...
By Akash Chavan
arXiv:2605.23916v2 Announce Type: replace-cross
Abstract: AI agents often pick tools from registries, where each tool's provider writes its description. We ask whether sales language in those descrip...
By Haochuan Kevin Wang, Zechen Zhang
We are introducing Structured Outputs in the API—model outputs now reliably adhere to developer-supplied JSON Schemas.
arXiv:2605.29313v2 Announce Type: replace
Abstract: LLM multi-agent systems often coordinate through natural-language dialogue or loosely structured shared memory, making intermediate state difficult...
By Shuyu Zhang, Yaqi Shi, Jiarui Zhang, Yanxiao Zhao, Lu Wang